Back to models
available
OpenAI: GPT-6 Luna
openai/gpt-6-lunaPrices
- Input
$0.10 per 1M tokens
verified- Input (>272k ctx)
$0.20 per 1M tokens
low- Input (batch, >272k ctx)
$0.10 per 1M tokens
low- Input (batch)
$0.05 per 1M tokens
verified- Input (batch) (long context)
$0.10 per 1M tokens
medium- Input (cache write, >272k ctx)
$0.25 per 1M tokens
low- Input (cache write, batch, >272k ctx)
$0.125 per 1M tokens
low- Input (cache write, batch)
$0.0625 per 1M tokens
verified- Input (cache write, batch) (long context)
$0.125 per 1M tokens
medium- Input (cache write, flex, >272k ctx)
$0.125 per 1M tokens
low- Input (cache write, flex)
$0.0625 per 1M tokens
verified- Input (cache write, flex) (long context)
$0.125 per 1M tokens
medium- Input (cache write, priority, >272k ctx)
$0.50 per 1M tokens
low- Input (cache write, priority)
$0.25 per 1M tokens
low- Input (cache write)
$0.125 per 1M tokens
verified- Input (cache write) (long context)
$0.25 per 1M tokens
medium- Input (cached read, >272k ctx)
$0.02 per 1M tokens
low- Input (cached read, batch, >272k ctx)
$0.01 per 1M tokens
low- Input (cached read, batch)
$0.005 per 1M tokens
verified- Input (cached read, batch) (long context)
$0.01 per 1M tokens
medium- Input (cached read, flex, >272k ctx)
$0.01 per 1M tokens
low- Input (cached read, flex)
$0.005 per 1M tokens
verified- Input (cached read, flex) (long context)
$0.01 per 1M tokens
medium- Input (cached read, priority, >272k ctx)
$0.04 per 1M tokens
low- Input (cached read, priority)
$0.02 per 1M tokens
low- Input (cached read)
$0.01 per 1M tokens
verified- Input (cached read) (long context)
$0.02 per 1M tokens
medium- Input (flex, >272k ctx)
$0.10 per 1M tokens
low- Input (flex)
$0.05 per 1M tokens
verified- Input (flex) (long context)
$0.10 per 1M tokens
medium- Input (long context)
$0.20 per 1M tokens
medium- Input (priority, >272k ctx)
$0.40 per 1M tokens
low- Input (priority)
$0.20 per 1M tokens
low- Output
$0.50 per 1M tokens
verified- Output (>272k ctx)
$0.75 per 1M tokens
low- Output (batch, >272k ctx)
$0.375 per 1M tokens
low- Output (batch)
$0.25 per 1M tokens
verified- Output (batch) (long context)
$0.375 per 1M tokens
medium- Output (flex, >272k ctx)
$0.375 per 1M tokens
low- Output (flex)
$0.25 per 1M tokens
verified- Output (flex) (long context)
$0.375 per 1M tokens
medium- Output (long context)
$0.75 per 1M tokens
medium- Output (priority, >272k ctx)
$1.50 per 1M tokens
low- Output (priority)
$1.00 per 1M tokens
low- Web search (context size: high)
$0.01 per query
low- Web search (context size: low)
$0.01 per query
low- Web search (context size: medium)
$0.01 per query
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Amazon Bedrock | Input | $0.11 per 1M tokens |
| Input (>272k ctx) | $0.22 per 1M tokens | |
| Input (>272k ctx) (region: global) | $0.20 per 1M tokens | |
| Input (>272k ctx) (region: us) | $0.22 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.275 per 1M tokens | |
| Input (cache write, >272k ctx) (region: global) | $0.25 per 1M tokens | |
| Input (cache write, >272k ctx) (region: us) | $0.275 per 1M tokens | |
| Input (cache write) | $0.1375 per 1M tokens | |
| Input (cache write) (region: global) | $0.125 per 1M tokens | |
| Input (cache write) (region: us) | $0.1375 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.022 per 1M tokens | |
| Input (cached read, >272k ctx) (region: global) | $0.02 per 1M tokens | |
| Input (cached read, >272k ctx) (region: us) | $0.022 per 1M tokens | |
| Input (cached read) | $0.011 per 1M tokens | |
| Input (cached read) (region: global) | $0.01 per 1M tokens | |
| Input (cached read) (region: us) | $0.011 per 1M tokens | |
| Input (region: global) | $0.10 per 1M tokens | |
| Input (region: us) | $0.11 per 1M tokens | |
| Output | $0.55 per 1M tokens | |
| Output (>272k ctx) | $0.825 per 1M tokens | |
| Output (>272k ctx) (region: global) | $0.75 per 1M tokens | |
| Output (>272k ctx) (region: us) | $0.825 per 1M tokens | |
| Output (region: global) | $0.50 per 1M tokens | |
| Output (region: us) | $0.55 per 1M tokens | |
| Microsoft Azure | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (>272k ctx) (region: eu) | $0.24 per 1M tokens | |
| Input (>272k ctx) (region: us) | $0.22 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write, >272k ctx) (region: eu) | $0.30 per 1M tokens | |
| Input (cache write, >272k ctx) (region: us) | $0.275 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cache write) (region: eu) | $0.15 per 1M tokens | |
| Input (cache write) (region: us) | $0.1375 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read, >272k ctx) (region: eu) | $0.024 per 1M tokens | |
| Input (cached read, >272k ctx) (region: us) | $0.022 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Input (cached read) (region: eu) | $0.012 per 1M tokens | |
| Input (cached read) (region: us) | $0.011 per 1M tokens | |
| Input (region: eu) | $0.12 per 1M tokens | |
| Input (region: us) | $0.11 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| Output (>272k ctx) (region: eu) | $0.90 per 1M tokens | |
| Output (>272k ctx) (region: us) | $0.825 per 1M tokens | |
| Output (region: eu) | $0.60 per 1M tokens | |
| Output (region: us) | $0.55 per 1M tokens | |
| Web search (context size: high) | $0.01 per query | |
| Web search (context size: low) | $0.01 per query | |
| Web search (context size: medium) | $0.01 per query | |
| Web search (region: eu, context size: high) | $0.01 per query | |
| Web search (region: eu, context size: low) | $0.01 per query | |
| Web search (region: eu, context size: medium) | $0.01 per query | |
| Web search (region: us, context size: high) | $0.01 per query | |
| Web search (region: us, context size: low) | $0.01 per query | |
| Web search (region: us, context size: medium) | $0.01 per query | |
| Microsoft Azure · azure-ai | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| Web search (context size: high) | $0.01 per query | |
| Web search (context size: low) | $0.01 per query | |
| Web search (context size: medium) | $0.01 per query | |
| OpenRouter · openai | Input | $0.10 per 1M tokens |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Query | $0.01 per query | |
| OpenRouter | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| GitHub Copilot · github-copilot | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| Other · cloudflare-ai-gateway | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| Other · crossmodel | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| Other · edenai | Input | $0.10 per 1M tokens |
| Input (>272k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272k ctx) | $0.75 per 1M tokens | |
| Other · kilo | Input | $0.10 per 1M tokens |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Other · llmgateway-providers | Input | $0.10 per 1M tokens |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Other · merge-gateway | Input | $0.10 per 1M tokens |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Other · nano-gpt | Input | $0.10 per 1M tokens |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Other · ofox | Input | $0.08 per 1M tokens |
| Input (cache write) | $0.10 per 1M tokens | |
| Input (cached read) | $0.008 per 1M tokens | |
| Output | $0.40 per 1M tokens | |
| Other · vercel | Input | $0.10 per 1M tokens |
| Input (>272.001k ctx) | $0.20 per 1M tokens | |
| Input (cache write, >272.001k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.125 per 1M tokens | |
| Input (cached read, >272.001k ctx) | $0.02 per 1M tokens | |
| Input (cached read) | $0.01 per 1M tokens | |
| Output | $0.50 per 1M tokens | |
| Output (>272.001k ctx) | $0.75 per 1M tokens |
Specifications
- Provider
- openai
- Context window
- 1,050,000
- Max output tokens
- 128,000
- Open weights
- no
- Released
- 09/22/2026
- Retires
- 03/11/2028
- First seen by this tracker
Price history
No price of this model has changed since we started tracking it.
- Input
- 0.1 per 1M tokens, unchanged since 09/23/2026
- Input (cached read)
- 0.01 per 1M tokens, unchanged since 09/23/2026
- Input (cache write)
- 0.125 per 1M tokens, unchanged since 09/23/2026
- Output
- 0.5 per 1M tokens, unchanged since 09/23/2026
- Input (long context)
- 0.2 per 1M tokens, unchanged since 09/23/2026
- Input (cached read) (long context)
- 0.02 per 1M tokens, unchanged since 09/23/2026
- Input (cache write) (long context)
- 0.25 per 1M tokens, unchanged since 09/23/2026
- Output (long context)
- 0.75 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, >272k ctx)
- 0.25 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, flex, >272k ctx)
- 0.125 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, priority, >272k ctx)
- 0.5 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, flex)
- 0.0625 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, priority)
- 0.25 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, >272k ctx)
- 0.02 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, flex, >272k ctx)
- 0.01 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, priority, >272k ctx)
- 0.04 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, batch)
- 0.005 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, batch, >272k ctx)
- 0.01 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, batch)
- 0.0625 per 1M tokens, unchanged since 09/23/2026
- Input (cache write, batch, >272k ctx)
- 0.125 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, flex)
- 0.005 per 1M tokens, unchanged since 09/23/2026
- Input (cached read, priority)
- 0.02 per 1M tokens, unchanged since 09/23/2026
- Input (>272k ctx)
- 0.2 per 1M tokens, unchanged since 09/23/2026
- Input (flex, >272k ctx)
- 0.1 per 1M tokens, unchanged since 09/23/2026
- Input (priority, >272k ctx)
- 0.4 per 1M tokens, unchanged since 09/23/2026
- Input (batch)
- 0.05 per 1M tokens, unchanged since 09/23/2026
- Input (batch, >272k ctx)
- 0.1 per 1M tokens, unchanged since 09/23/2026
- Input (flex)
- 0.05 per 1M tokens, unchanged since 09/23/2026
- Input (priority)
- 0.2 per 1M tokens, unchanged since 09/23/2026
- Output (>272k ctx)
- 0.75 per 1M tokens, unchanged since 09/23/2026
- Output (flex, >272k ctx)
- 0.375 per 1M tokens, unchanged since 09/23/2026
- Output (priority, >272k ctx)
- 1.5 per 1M tokens, unchanged since 09/23/2026
- Output (batch)
- 0.25 per 1M tokens, unchanged since 09/23/2026
- Output (batch, >272k ctx)
- 0.375 per 1M tokens, unchanged since 09/23/2026
- Output (flex)
- 0.25 per 1M tokens, unchanged since 09/23/2026
- Output (priority)
- 1 per 1M tokens, unchanged since 09/23/2026
- Web search (context size: high)
- 0.01 per query, unchanged since 09/23/2026
- Web search (context size: low)
- 0.01 per query, unchanged since 09/23/2026
- Web search (context size: medium)
- 0.01 per query, unchanged since 09/23/2026
- Input (batch) (long context)
- 0.1 per 1M tokens, unchanged since 10/01/2026
- Input (cached read, batch) (long context)
- 0.01 per 1M tokens, unchanged since 10/01/2026
- Input (cache write, batch) (long context)
- 0.125 per 1M tokens, unchanged since 10/01/2026
- Output (batch) (long context)
- 0.375 per 1M tokens, unchanged since 10/01/2026
- Input (flex) (long context)
- 0.1 per 1M tokens, unchanged since 10/01/2026
- Input (cached read, flex) (long context)
- 0.01 per 1M tokens, unchanged since 10/01/2026
- Input (cache write, flex) (long context)
- 0.125 per 1M tokens, unchanged since 10/01/2026
- Output (flex) (long context)
- 0.375 per 1M tokens, unchanged since 10/01/2026